Elevenlabs just got wrecked. This free AI text to speech is WILD!
YouTube transcript, YouTube translate
A quick preview of the first subtitles so you know what the video covers.
This is the best text to speech generator you can use right now . You can easily clone anyone's voice . It's so good at handling emotions . It can even do accents and different languages . You can even prompt the exact voice you want . It works with low VRAM and is super fast . We have a new free and open-source texttospech generator which is state-of-the-art . So Alibaba just released Quen 3 text to speech and this is super powerful and flexible . You can clone anyone with just a few seconds of their voice or you can enter a prompt describing exactly what voice you want and it can generate a completely new voice. It's multilingual. It can handle a ton of different languages and it's really good at actually capturing the emotions and intent of your transcript instead of just me talking . Here are some examples . So, here's an example where we can enter a prompt describing exactly how we want the voice to sound like . For example, there's going to be an initial laugh . It's going to be rapid and then slowing to a deliberate pace . There's going to be a loud laugh transitioning to a standard conversational level, etc., etc . And then here is the transcript . Good one. Okay, fine . I'm just going to leave this sock monkey here . Goodbye. It . It can definitely do more expressive stuff like laughter as you can hear . Or next, you can also specify the age . So here we have a sarcastic, assertive teenage girl with crisp inunciation, controlled volume, etc., etc . And then here's the transcript, blah blah blah . We're all very fascinated, Whitey, but we'd like to get paid . Pretty good . Or here's another example. . Here we have a middle-aged adult, authoritative, confident, and performative